{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 19.999384615384617,
  "global_step": 8120,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "eval_loss": 0.3488372266292572,
      "eval_mse": 0.3488372266292572,
      "eval_runtime": 3.205,
      "eval_samples_per_second": 156.005,
      "eval_steps_per_second": 19.657,
      "step": 406
    },
    {
      "epoch": 1.23,
      "learning_rate": 1.1989617996694624e-05,
      "loss": 0.8208,
      "step": 500
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.3489202857017517,
      "eval_mse": 0.3489202857017517,
      "eval_runtime": 3.0732,
      "eval_samples_per_second": 162.695,
      "eval_steps_per_second": 20.5,
      "step": 812
    },
    {
      "epoch": 2.46,
      "learning_rate": 1.1202897655704163e-05,
      "loss": 0.1606,
      "step": 1000
    },
    {
      "epoch": 3.0,
      "eval_loss": 0.3954257369041443,
      "eval_mse": 0.3954257369041443,
      "eval_runtime": 3.1411,
      "eval_samples_per_second": 159.182,
      "eval_steps_per_second": 20.057,
      "step": 1218
    },
    {
      "epoch": 3.69,
      "learning_rate": 1.0416177314713701e-05,
      "loss": 0.1174,
      "step": 1500
    },
    {
      "epoch": 4.0,
      "eval_loss": 0.22338131070137024,
      "eval_mse": 0.22338134050369263,
      "eval_runtime": 3.2318,
      "eval_samples_per_second": 154.71,
      "eval_steps_per_second": 19.493,
      "step": 1624
    },
    {
      "epoch": 4.93,
      "learning_rate": 9.62945697372324e-06,
      "loss": 0.0932,
      "step": 2000
    },
    {
      "epoch": 5.0,
      "eval_loss": 0.22499865293502808,
      "eval_mse": 0.22499865293502808,
      "eval_runtime": 3.0935,
      "eval_samples_per_second": 161.631,
      "eval_steps_per_second": 20.366,
      "step": 2030
    },
    {
      "epoch": 6.0,
      "eval_loss": 0.24710388481616974,
      "eval_mse": 0.24710386991500854,
      "eval_runtime": 3.1479,
      "eval_samples_per_second": 158.836,
      "eval_steps_per_second": 20.013,
      "step": 2436
    },
    {
      "epoch": 6.16,
      "learning_rate": 8.84273663273278e-06,
      "loss": 0.0729,
      "step": 2500
    },
    {
      "epoch": 7.0,
      "eval_loss": 0.16448178887367249,
      "eval_mse": 0.16448178887367249,
      "eval_runtime": 3.1325,
      "eval_samples_per_second": 159.618,
      "eval_steps_per_second": 20.112,
      "step": 2842
    },
    {
      "epoch": 7.39,
      "learning_rate": 8.056016291742319e-06,
      "loss": 0.0628,
      "step": 3000
    },
    {
      "epoch": 8.0,
      "eval_loss": 0.16940604150295258,
      "eval_mse": 0.16940604150295258,
      "eval_runtime": 3.1022,
      "eval_samples_per_second": 161.174,
      "eval_steps_per_second": 20.308,
      "step": 3248
    },
    {
      "epoch": 8.62,
      "learning_rate": 7.2692959507518586e-06,
      "loss": 0.0542,
      "step": 3500
    },
    {
      "epoch": 9.0,
      "eval_loss": 0.13145290315151215,
      "eval_mse": 0.13145291805267334,
      "eval_runtime": 3.1898,
      "eval_samples_per_second": 156.749,
      "eval_steps_per_second": 19.75,
      "step": 3654
    },
    {
      "epoch": 9.85,
      "learning_rate": 6.482575609761398e-06,
      "loss": 0.0477,
      "step": 4000
    },
    {
      "epoch": 10.0,
      "eval_loss": 0.16126562654972076,
      "eval_mse": 0.16126562654972076,
      "eval_runtime": 3.1805,
      "eval_samples_per_second": 157.209,
      "eval_steps_per_second": 19.808,
      "step": 4060
    },
    {
      "epoch": 11.0,
      "eval_loss": 0.13891386985778809,
      "eval_mse": 0.13891386985778809,
      "eval_runtime": 3.0894,
      "eval_samples_per_second": 161.843,
      "eval_steps_per_second": 20.392,
      "step": 4466
    },
    {
      "epoch": 11.08,
      "learning_rate": 5.695855268770936e-06,
      "loss": 0.0416,
      "step": 4500
    },
    {
      "epoch": 12.0,
      "eval_loss": 0.11093080043792725,
      "eval_mse": 0.11093080043792725,
      "eval_runtime": 3.178,
      "eval_samples_per_second": 157.331,
      "eval_steps_per_second": 19.824,
      "step": 4872
    },
    {
      "epoch": 12.32,
      "learning_rate": 4.909134927780475e-06,
      "loss": 0.0369,
      "step": 5000
    },
    {
      "epoch": 13.0,
      "eval_loss": 0.15438133478164673,
      "eval_mse": 0.15438130497932434,
      "eval_runtime": 3.1682,
      "eval_samples_per_second": 157.816,
      "eval_steps_per_second": 19.885,
      "step": 5278
    },
    {
      "epoch": 13.55,
      "learning_rate": 4.122414586790015e-06,
      "loss": 0.0337,
      "step": 5500
    },
    {
      "epoch": 14.0,
      "eval_loss": 0.11555473506450653,
      "eval_mse": 0.11555473506450653,
      "eval_runtime": 3.1267,
      "eval_samples_per_second": 159.911,
      "eval_steps_per_second": 20.149,
      "step": 5684
    },
    {
      "epoch": 14.78,
      "learning_rate": 3.335694245799554e-06,
      "loss": 0.0299,
      "step": 6000
    },
    {
      "epoch": 15.0,
      "eval_loss": 0.14125587046146393,
      "eval_mse": 0.14125585556030273,
      "eval_runtime": 3.1173,
      "eval_samples_per_second": 160.395,
      "eval_steps_per_second": 20.21,
      "step": 6090
    },
    {
      "epoch": 16.0,
      "eval_loss": 0.12824614346027374,
      "eval_mse": 0.12824612855911255,
      "eval_runtime": 3.141,
      "eval_samples_per_second": 159.185,
      "eval_steps_per_second": 20.057,
      "step": 6496
    },
    {
      "epoch": 16.01,
      "learning_rate": 2.5489739048090933e-06,
      "loss": 0.0288,
      "step": 6500
    },
    {
      "epoch": 17.0,
      "eval_loss": 0.11662615835666656,
      "eval_mse": 0.11662616580724716,
      "eval_runtime": 3.2355,
      "eval_samples_per_second": 154.536,
      "eval_steps_per_second": 19.471,
      "step": 6902
    },
    {
      "epoch": 17.24,
      "learning_rate": 1.7622535638186322e-06,
      "loss": 0.0263,
      "step": 7000
    },
    {
      "epoch": 18.0,
      "eval_loss": 0.12519659101963043,
      "eval_mse": 0.12519659101963043,
      "eval_runtime": 3.1453,
      "eval_samples_per_second": 158.968,
      "eval_steps_per_second": 20.03,
      "step": 7308
    },
    {
      "epoch": 18.47,
      "learning_rate": 9.755332228281715e-07,
      "loss": 0.0252,
      "step": 7500
    },
    {
      "epoch": 19.0,
      "eval_loss": 0.13828542828559875,
      "eval_mse": 0.13828542828559875,
      "eval_runtime": 3.121,
      "eval_samples_per_second": 160.203,
      "eval_steps_per_second": 20.186,
      "step": 7714
    },
    {
      "epoch": 19.7,
      "learning_rate": 1.8881288183771059e-07,
      "loss": 0.0236,
      "step": 8000
    },
    {
      "epoch": 20.0,
      "eval_loss": 0.11976799368858337,
      "eval_mse": 0.11976799368858337,
      "eval_runtime": 3.0971,
      "eval_samples_per_second": 161.439,
      "eval_steps_per_second": 20.341,
      "step": 8120
    },
    {
      "epoch": 20.0,
      "step": 8120,
      "total_flos": 8550922763068416.0,
      "train_loss": 0.10351273032832028,
      "train_runtime": 5208.5032,
      "train_samples_per_second": 24.959,
      "train_steps_per_second": 1.559
    }
  ],
  "max_steps": 8120,
  "num_train_epochs": 20,
  "total_flos": 8550922763068416.0,
  "trial_name": null,
  "trial_params": null
}